Profile avatar
romanklinger.de
professor for natural language processing, head of BamNLP @bamnlp.de 📍 Duisburg, Stuttgart, Bamberg #NLProc #emotion #sentiment #factchecking #argumentmining #informationextraction #bionlp
40 posts 1,023 followers 382 following
Regular Contributor
Active Commenter

Today, we had Goran Glavaš from @uni-wuerzburg.de in our research seminar for a talk "On Multilingual Abilities of (Different Types of) Language Models" at @bamnlp.de @uni-bamberg.de Thanks for visiting us, Goran!

Our @bamnlp.de group at @uni-bamberg.de starts to generate output :-). Let's meet in Vienna!

I'll give a talk this Thursday at 5:45 at Universität zu Köln: "Adapting Language Models for the Analysis of Real World Textual Data – Train the model, change the prompt, or adapt the data?" – the talk is based on aclanthology.org/2025.coling-... and arxiv.org/abs/2412.11653 #NLProc

We (@csindermann.bsky.social and @romanklinger.de) prepare project to develop a novel annotation/data acquisition platform. To understand limitations of current systems, we could use your help. If your research involves collecting data, could you fill this form? tinyurl.com/annotation20... Thanks!

Are you interested to dive deeper into bridging #psychology and natural language processing #nlproc? We are organizing a new workshop (collocated with icwsm.org in Copenhagen, taking place on June 23. Paper deadline is March 21st. More information: nlpsi-workshop.github.io

Choose-a-chair fair at the computer science faculty @uni-bamberg.de – we presented our courses and theses topics to our students (with Sean Papay, @multilingual-s.bsky.social and @romanklinger.de).

I'll give a talk at the @fau.de in Erlangen this Thursday (2025–01–30, 16:15h; www.linguistik.phil.fau.de/2025/01/22/v...). I'll talk about studies in which we collected data for building #NLP #NLPproc models via psychology(-inspired) data acquisition methods (for emotions, coping, deception).

Got a 4 in ACL Rolling Review from the Action Editor, committed to @naaclmeeting.bsky.social – and got a rejection. This process is frustrating. I want to go back to conference-level reviewing and decisions... I like the revise/resubmit idea, but this way it's more random than before... #nlp #nlproc

Are you at #COLING2025? Come visit our poster presented by Yarik Menchaca Resendiz on "MOPO: Multi-Objective Prompt Optimization for Affective Text Generation". (Fri, Jan 24 13:30-15:00) #NLP #nlproc #prompts #llm #emotions

9 more days until application deadline

The @bamnlp.de group wishes everybody nice holidays. 🎄

Have a look at our new #preprint on our work on human-in-the-loop prompt optimization. It's a preprint of a demo paper describing our experiment environment that we use in the @dfgpublic.bsky.social funded project INPROMPT. #nlp #nlproc

New #preprint by @nlp-amelie.bsky.social and @romanklinger.de on automatically optimizing a claim paraphrased/extractor with preference optimization, such that the claims can be better fact-checked. #nlp #nlproc

I've been invited by the student body @fachschaftwiai.toot.kif.rocks.ap.brid.gy of our CS department to give one of the christmas lectures. If you are interested to hear my ideas how to use #NLP #NLProc methods to analyze data that emerges from X-Mas related tasks, have a look: youtu.be/7wOpIM9_lRQ

Want to learn how to lie (or detect lies)? Have a look at our unified deception corpus! #nlproc #nlp

I've been invited by the student body @fachschaftwiai.toot.kif.rocks.ap.brid.gy of our CS department to give one of the christmas lectures. If you are interested to hear my ideas how to use #NLP #NLProc methods to analyze data that emerges from X-Mas related tasks, have a look: youtu.be/7wOpIM9_lRQ

I started my position at the University of Bamberg nine months ago. I didn't know Bamberg (en.wikipedia.org/wiki/Bamberg) before coming here, but I must say: I like this town.

One paper accepted at #COLING #NLP #NLProc

Today, Eyke HĂĽllermeier gave a talk in our BACAI lecture series, on uncertainty quantification in machine learning. The main message was the difference between inherent randomness and a lack of knowledge: aleatoric and epistemic uncertainty.

I really like ACL Rolling Review @aclmeeting.bsky.social but I am not ok with having only three days for the answers, spanning over the weekend... Can we please do that differently in the future? #NLProc

New here (as nearly everybody), so I'd like to briefly introduce myself. I am working in natural language processing #NLP #NLProc – the field in computer science and linguistics that teaches computers to understand, generate, and process human language. (1/4)

What's happened to X proves the need for Bluesky. The future company is a possible adversary. We make decisions knowing that we won't always be here or won't always be able to control the company's decisions. It's why we've given you the freedom of exit to go elsewhere w your followers and data.